The thing I’m most curious about is: There are new context management and memory features in the API —
https://www.anthropic.com/news/context-management
Anyone know if these are used in Claude-Code?
Claude Code 2.0
311–320 of 431 posts
Re: Claude Code 2.0
#312Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…
Incredibly dangerous to use? Seems like a wild exaggeration. I’ve been using Claude code since launch, must have used it for 1000 hours or more by now, and it’s never done anything I didn’t want it to do. Why would I run it in a sandbox? It writes code for me and occasionally runs a build and tests. I’m not sure why you’re so fixated on the “danger”, when you use these things all the time you end up realizing that th…
Because it grabs the headlines and upvotes more. It is becoming quite the bore to read as it offers nothing new, or an accurate representation of the facts. Thanks for calling it out. Same experience regarding thousands of hours of usage since launch, tested from sandboxed docker to take over an entire macbook air and here's an ssh login to a dev server whilst you're at it. I spot check with audits every other day and only wish for more autonomy with the agents, over less.
Re: Claude Code 2.0
#313Earlier quoted context omitted.
You can rewind your context back to the checkpoint
That is nice, but it makes me wonder how little people actually know and use git nowadays. This is after all, something git really shines at. Still good to see! (It's not like I can't still just use git for that, which I fully intend to do)
- you DONT want your personal Claude conversation in your repo
- you DO want your prompts and state synced (going back to a point in the prompt going back to a point in the code).
Git is a non starter then. At least the repo’s same git.
Plus, you probably don’t want the agent to run mutating git commands, just in case it decides to allucinate a push —force
Re: Claude Code 2.0
#314Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…
Instead of containers, which may not always be available, I'm experimenting with having control over the shell to whitelist the commands that the LLM can run [0]. Similar to an allow list, but configured outside the terminal agent. Also trying to make it easy to use the same technique in macOS and Linux [0]: https://ricardoanderegg.com/posts/control-shell-permissions-...
Not specific to LLM stuff, but I've lately been using bubblewrap more and more to isolate bits of software that are somewhat more sketchy (NPM stuff, binaries downloaded from GitHub, honestly most things not distro-packaged). It was a little rocky start out with, but it is nice knowing that a random binary can't snoop on and exfiltrate e.g. my shell history.
Re: Claude Code 2.0
#315Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…
Incredibly dangerous to use? Seems like a wild exaggeration. I’ve been using Claude code since launch, must have used it for 1000 hours or more by now, and it’s never done anything I didn’t want it to do. Why would I run it in a sandbox? It writes code for me and occasionally runs a build and tests. I’m not sure why you’re so fixated on the “danger”, when you use these things all the time you end up realizing that th…
It is dangerous.
Just yesterday my cursor agent made some changes to a live kubernetes cluster even over my specific instruction not to. I gave it kubectl to analyze and find the issues with a large Prometheud + AlertManager configuration, then switched windows to work on something else.
When I was back the MF was patching live resources to try and diagnose the issue.
Re: Claude Code 2.0
#316Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…
Incredibly dangerous to use? Seems like a wild exaggeration. I’ve been using Claude code since launch, must have used it for 1000 hours or more by now, and it’s never done anything I didn’t want it to do. Why would I run it in a sandbox? It writes code for me and occasionally runs a build and tests. I’m not sure why you’re so fixated on the “danger”, when you use these things all the time you end up realizing that th…
The original opus/sonnet 4 safety card mentioned that it would hand write emails to the fbi turning in a user if it thought they were doing something really bad. It has examples of the “snitch” emails.
I too use it extensively. But they’re very, very capable models, and the command line contains a bunch of ways to exfiltrate data off your system if it wants to.
Re: Claude Code 2.0
#317Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…
Dangerous how? Claude code literally asks before running any command.
I suppose they’re dangerous in the same way any terminal shell is dangerous, but it seems a bit of a moral panic. All tools can be dangerous if misused.
Re: Claude Code 2.0
#318Earlier quoted context omitted.
Incredibly dangerous to use? Seems like a wild exaggeration. I’ve been using Claude code since launch, must have used it for 1000 hours or more by now, and it’s never done anything I didn’t want it to do. Why would I run it in a sandbox? It writes code for me and occasionally runs a build and tests. I’m not sure why you’re so fixated on the “danger”, when you use these things all the time you end up realizing that th…
The original opus/sonnet 4 safety card mentioned that it would hand write emails to the fbi turning in a user if it thought they were doing something really bad. It has examples of the “snitch” emails. I too use it extensively. But they’re very, very capable models, and the command line contains a bunch of ways to exfiltrate data off your system if it wants to.
That’s a pretty wild misrepresentation. The actual statement was from red team testing in a very contrived and intentional setup designed to test refusal in extreme circumstances.
Yes, it was a legit safety issue and worth being aware of, but it’s not it was a general case. Red teamers worked hard to produce that result.
Re: Claude Code 2.0
#319Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…
They're only as dangerous as the capabilities you give them. I just created a `codex` and `claude` user on my Linux box and practically always run in yolo mode. I've not had a problem so far. Also, I think shellagent sounds cooler.
I have run it in a podman container and I mount the project directory.
Re: Claude Code 2.0
#320Earlier quoted context omitted.
Incredibly dangerous to use? Seems like a wild exaggeration. I’ve been using Claude code since launch, must have used it for 1000 hours or more by now, and it’s never done anything I didn’t want it to do. Why would I run it in a sandbox? It writes code for me and occasionally runs a build and tests. I’m not sure why you’re so fixated on the “danger”, when you use these things all the time you end up realizing that th…
It is dangerous. Just yesterday my cursor agent made some changes to a live kubernetes cluster even over my specific instruction not to. I gave it kubectl to analyze and find the issues with a large Prometheud + AlertManager configuration, then switched windows to work on something else. When I was back the MF was patching live resources to try and diagnose the issue.
But this is just like giving a junior engineer access to a prod K8s cluster and having them work for hours on stuff related to said cluster... you wouldn't do it. Or at least, I wouldn't do it.
In my own career, when I was a junior, I fucked up a prod database... which is why we generally don't give junior/associate people to much access to critical infra. Junior Engineers aren't "dangerous" but we just don't give them too much access/authority too soon.
Claude Code is actually way smarter than a junior engineer in my experience, but I wouldn't give it direct access to a prod database or servers, it's not needed.